viola.SV_signature_extractor

SV_signature_extractor(X, n_iter=10, name='test', **sklearn_nmf_parameters)

Parameters

• X (ndarray or pd.DataFrame) – (n_sample, n_features) shaped ndarray.

• n_iter (int) – Number of iteration for resampling X.

• name (str or int) – Name of this run. Do not use ‘_’ in this argument.

• **sklearn_nmf_parameters (dict) – kwargs to pass the sklearn.decomposition.NMF (https://scikit-learn.org/stable/modules/generated/sklearn.decomposition.NMF.html). Specify number of signatures to the ‘n_components’ argument.

Returns

• result_silhouette (float) – Average silhouette score of the extracted SV signatures

• result_metrics (float) – beta_loss of the extracted matrice.

• exposure_matrix ((n_samples, n_signatures)) – Exposure matrix.

• signature_matrix ((n_signatures, n_features)) – SV signature matrix extracted.